Brecht Van Lommel 16204bd647 Cycles: prepare to make CUDA 5.0 the official version we use ...

* Add CUDA compiler version detection to cmake/scons/runtime
* Remove noinline in kernel_shader.h and reenable --use_fast_math if CUDA 5.x
  is used, these were workarounds for CUDA 4.2 bugs
* Change max number of registers to 32 for sm 2.x (based on performance tests
  from Martijn Berger and confirmed here), and also for NVidia OpenCL.

Overall it seems that with these changes and the latest CUDA 5.0 download, that
performance is as good as or better than the 2.67b release with the scenes and
graphics cards I tested.

2013-06-19 17:54:23 +00:00

..

CMakeLists.txt

add missing bullet header to cmake, quiet reports from 'make test_cmake'

2013-02-06 04:16:28 +00:00

device_cpu.cpp

Cycles:

2013-05-14 21:18:20 +00:00

device_cuda.cpp

Cycles: prepare to make CUDA 5.0 the official version we use

2013-06-19 17:54:23 +00:00

device_intern.h

Fix #33107: cycles fixed threads 1 was still having two cores do work,

2012-11-07 21:00:49 +00:00

device_memory.h

Cycles: code refactoring to add generic lookup table memory.

2013-04-01 20:26:43 +00:00

device_multi.cpp

Cycles: memory usage report

2012-11-05 08:04:57 +00:00

device_network.cpp

Cycles:

2013-02-21 17:10:14 +00:00

device_network.h

Cycles:

2013-05-14 21:18:20 +00:00

device_opencl.cpp

Cycles: prepare to make CUDA 5.0 the official version we use

2013-06-19 17:54:23 +00:00

device_task.cpp

Cycles:

2013-05-14 21:18:20 +00:00

device_task.h

Cycles:

2013-05-14 21:18:20 +00:00

device.cpp

Fix #33243: cycles CUDA going missing sometimes, disabled the new code now that

2012-11-20 17:39:56 +00:00

device.h

Cycles: deal a bit better with errors when CUDA runs out of memory, try to avoid crashes.

2012-12-23 12:53:58 +00:00